Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Hybrid Deep Learning Model for Hippocampal Localization in Alzheimer's Diagnosis Using U-Net and VGG16
Full text linkAlzheimer's disease (AD) is a complex neurodegenerative disease that involves considerable challenges in accurately diagnosing and locating the?affected brain regions. This paper?proposes a new fusion model based on VGG16 and U-Net to achieve accurate segmentation of hippocampus localization and improve AD diagnostic accuracy. Compared to previous techniques such as hierarchical fully?convolutional networks (FCNs) or LBP-TOP localization (an accuracy range of 68% to 95%), our approach achieved a superior accuracy (98.6%) with a mean Jaccard index of 97.3%, like the predicted accuracy range of conventional imaging analysis techniques. By utilizing pre-trained transfer learning models and sophisticated data augmentation methods,?generalization to different datasets greatly reduced over-fitting. Although existing approaches?usually require labor-intensive segmentation or employ handcrafted features, our model automates the hippocampus's localization, leading to improved efficiency and scalability. The effectiveness of our method is strongly supported by the performance metrics including Mean Squared Error (MSE) and Avg. error Standard Deviation which show that MSE values were 5 times lower than those produced using the Hough-CNN based?approach (0.0507 vs. 4.4%). Real-world demands include the need for minimal computational complexity and dependence?on pre-processed ADNI MRI datasets compromising generalizability in actual clinical frameworks. Our results?demonstrated that the fusion model yields superior hippocampal segmentation performance and a new standard for AD diagnostic scores, making a substantial impact on both academic and clinical domains
A comparative study on SMOTE, CTGAN, and hybrid SMOTE-CTGAN for medical data augmentation
Full text linkThe imbalance of clinical datasets remains a challenge in medical data mining, often resulting in models biased toward majority outcomes and reduced sensitivity to rare but clinically critical cases. This study presents a comparative evaluation of three augmentation strategies—Synthetic Minority Oversampling Technique (SMOTE), Conditional Tabular GAN (CTGAN), and a hybrid SMOTE+CTGAN—on the Framingham Heart Study dataset for cardiovascular disease prediction. Augmented datasets were evaluated using Decision Tree, Random Forest, and XGBoost classifiers across multiple metrics, including accuracy, precision, recall, and F1-score. Results demonstrate that classifiers trained on imbalanced data achieved high accuracy but poor minority recall (0.40), confirming model’s bias toward majority class. SMOTE yielded the strongest improvements in minority recall (up to 0.88 with XGBoost) and balanced F1 across classes, though at the cost of reduced majority recall. CTGAN and SMOTE+CTGAN delivered more moderate improvements in minority recall (0.66–0.77) while preserving higher majority recall (0.86), providing a gentler trade-off. These findings indicate that while SMOTE remains a robust baseline for addressing imbalance, hybrid and GAN-based approaches offer practical alternatives for preserving majority performance. The results highlight that augmentation choice should be informed by clinical context
Visual symbolism and the art–design nexus in madness: a critical discourse analysis of penahitam’s subcultural artzine in Indonesia
No full textThis study examines how hybrid visual practices in subcultural contexts challenge the binary between art and design. It addresses the theoretical division proposed by Tsion Avital, who posits a strict dichotomy between symbolic art and functional design. Using this framework, the visual discourse of the Indonesian collective Penahitam is critically analyzed. The 9th edition of Penahitam's artzine, Madness, is selected as a case study due to its thematic depth and ideological complexity. The research applies Norman Fairclough’s Critical Discourse Analysis (CDA) to integrate textual, visual, and contextual elements, exploring how meaning is constructed through the interplay of image, text, layout, and cultural production. Avital’s symbolic-functional theory serves as a lens to assess how Penahitam negotiates between expressive freedom and visual functionality.Findings indicate that Madness reconfigures the relationship between artistic and design elements into a hybrid visual discourse. The artzine's layout, poetic writing, dark-art illustrations, and socio-political content work cohesively to communicate ideological resistance while remaining accessible. This integration disrupts Avital’s dichotomy, showing how hybridity becomes a strategic tool for expression and subcultural authorship. Furthermore, the production and dissemination of the artzine across 29 Indonesian cities underscore Penahitam’s commitment to collective authorship, independence, and decentralized cultural activism. This study contributes to the discourse on art-design hybridity by offering a concrete analytical model for understanding how independent collectives use visual media to challenge dominant narratives and assert creative autonomy
Real-Time Autonomous Vehicle Navigation via Rule-Based Waypoint Selection and Spline-Guided MPC
Full text linkThis paper presents a robust and efficient Localized Spline-based Path-Planning (LSPP) algorithm aimed at improving autonomous highway navigation. LSPP uniquely combines localized quintic splines with a speed-profile optimizer to generate smooth, dynamically feasible trajectories that prioritize obstacle avoidance, passenger comfort, and strict adherence to road constraints such as lane boundaries. By leveraging real-time data from the vehicle’s sensor fusion module, LSPP accurately interprets the positions of nearby vehicles and obstacles, producing safe paths that are passed to the Model Predictive Control (MPC) module for precise execution. Simulations show LSPP reduces lateral jerk by 30% and computation time by 25% compared to Bézier-based methods, confirming enhanced comfort and efficiency. Extensive testing across diverse highway scenarios further demonstrates LSPP’s superior performance in trajectory smoothness, lane-keeping, and responsiveness over traditional approaches, validating it as a compelling solution for safe, comfortable, and efficient autonomous highway driving
Efficient Detection Classifiers for Genetically-Modified Golden Rice Via Machine Learning
Full text linkRice is a staple food for over half of the global population, especially in the Philippines. However, traditional rice lacks essential micronutrients like vitamin A, contributing to widespread Vitamin A Deficiency (VAD). Golden Rice was developed to combat VAD, and this is biofortified with beta-carotene, a precursor of Vitamin A. However, concerns about cross-contamination, food safety, and ethics have emerged. Current GMO detection methods, such as PCR and ELISA, are not ideal for large-scale or on-site use since these are intended to be performed inside laboratory and requires technical expertise. This study presents a novel machine learning (ML)-based approach for the detection of genetically modified Golden Rice using RGB image data and several classification models as an efficient, rapid, non-destructive method to detect GMO Golden Rice. Two datasets of rice images (340 samples of GMO Golden Rice and 340 samples of Traditional Rice) were processed and split for training and testing (80-20 ratio). This study found that WEKA's Random Tree and MATLAB's Trilayered Neural Network achieved 100% accuracy in detecting GMO Golden Rice, with the fastest computational efficiency in their respective platforms. Additional metrics, such as Precision and Recall, further verified the robustness of these classifiers. This research lays the foundation for developing portable, field-deployable detection tools to empower farmers and regulators while enhancing consumer trust in GMO labeling. Furthermore, the application of ML to GMO rice detection opens new possibilities for biofortified crop monitoring. Future work may explore integrating additional rice features and GMO varieties, validating the results, and expanding this methodology to other GMO rice variants and hybrid varieties to further enhance detection accuracy and scalability
The use of silence as a monitor in EAL Australia
Full text linkThis mixed methods study has highlighted that students in lower level of EAL in Ausytalia have used silence to monitor their speeches. The study surveyed 148 student and teachers and results highlighted that teachers did not know about the adult silent period. Findings show that that their silent period was not treated by their teachers due to ‘pedagogical barriers’. Competent Bilinguals said that there was too much emphasis on form rather than meaning. The main reason for paucity on the this topic is because for several decades the teaching of English as an additional language (EAL) has focused on communicative language teaching (CLT) to encourage students to use English to make meaningful conversations. Proficency silence as an adult learnier in EAL is crusal and needs to understood by educators
An Exploratory Study of Students Perceptions of Using ChatGPT in Undergraduate Thesis Writing
No full textChatGPT, an artificial intelligence-based technology developed byOpenAI, exhibits remarkable capabilities in addressing a wide range ofinquiries and has emerged as a transformative tool in the realm ofscientific research. Despite its potential, the extent to which ChatGPTcan assist undergraduate students in thesis writing remainsunderexplored. This study seeks to investigate students#39; perceptionsregarding the utilization of ChatGPT in the process of undergraduatethesis composition. Employing a qualitative research methodology, datawere collected through semi-structured interviews with students fromthe Faculty of Computer Science at Universitas Brawijaya. Thematicanalysis was utilized to examine the data, revealing a spectrum ofstudent perspectives on the application of ChatGPT in thesis writing.While students acknowledge that ChatGPT enhances writing efficiencyand improves work quality through its various capabilities, they alsorecognize its limitations, particularly concerning the accuracy andreliability of information. Moreover, students express concerns aboutthe potential for over-reliance on ChatGPT, which could impede thedevelopment of creativity, research skills, and critical thinking
Beyond likes and follows understanding social media's grip on adolescent mental health
Full text linkThis study aims to examine the psychological effects of social media use on adolescents, with particular attention to how patterns of digital interaction influence symptoms of anxiety, depression, and self-esteem. It seeks to understand not only the extent of these effects but also the underlying mechanisms—especially the role of social comparison and the pursuit of online validation within the broader context of the attention economy. Adopting a mixed-methods approach, this research integrates quantitative data from a survey of 500 high school students aged 13–18 with qualitative insights drawn from in-depth interviews with 20 adolescents. The survey measures the frequency and intensity of social media use, emotional responses to online interactions, and self-reported mental health outcomes using validated psychological instruments. The qualitative component enriches the findings by exploring how adolescents interpret their online experiences, internalize digital norms, and navigate the pressures of social media culture. Findings indicate a significant correlation between high-frequency social media use and increased levels of anxiety and depressive symptoms, especially among female participants. Respondents frequently reported feelings of inadequacy, social pressure, and sleep disturbances linked to online comparison and fear of missing out (FOMO). The contribution of this research lies in its comprehensive and context-sensitive examination of adolescent social media engagement, offering both empirical evidence and theoretical insight into the psychosocial vulnerabilities exacerbated by digital platforms. By combining statistical trends with personal narratives, the study adds depth to ongoing discussions about youth mental health in the digital age. It further advocates for the development of digital literacy education and mental health interventions that are responsive to the lived realities of adolescents growing up in algorithmically curated social environments
Enhancing MG996R Servo Motor Performance Using PSO-Tuned PID and Feedforward Control
Full text linkThe aim of this research is to improve the precision of factory-locked MG996R servo motors, which are frequently employed in biomedical and robotic applications. These motors are characterized by the absence of inherent feedback channels and adjustable internal settings. The proposed technique proposes a non-invasive control strategy that utilizes externally obtained feedback to enable closed-loop control without requiring any modifications to the interior circuitry. The scientific contribution consists of the development of an outer-loop PID control framework that has been optimized using Particle Swarm Optimization (PSO) and enhanced with feedforward compensation. By utilizing the inherent potentiometer, this method ensures the preservation of hardware integrity and enables real-time angle feedback. A model fit of 96.94% was achieved by establishing a second-order discrete-time model using MATLAB's System Identification Toolbox. Particle Swarm Optimization (PSO) was employed to optimize PID improvements offline by minimizing the Integral of Squared Error (ISE). In both experimental and simulated environments, the controller's effectiveness was assessed using 2 rad/s sine wave inputs and a 10° step. The PSO-PID with feedforward controller achieved optimal results, achieving an RMSE of 0.5313° and an MAE of 0.1630° in simulations, as well as an MAE of 0.8497° in hardware step response. The requirement for gain scaling in embedded systems was underscored by the instability of the standalone PSO-PID controller. This method offers a pragmatic, scalable solution for applications such as assistive robotics, prosthetic joints, and surgical instruments. In order to achieve sub-degree precision in safety-critical environments, future endeavors will entail the implementation of adaptive gain tuning and enhanced resolution sensing
Fractional-Order Discrete Predator–Prey System of Leslie Type: Existence, Stability, and Numerical Simulation
Full text linkThis study explores a fractional-order (FO) discrete predator prey (PP) system of Leslie type (LT) by incorporating fractional differences in the Caputo-Fabrizio-Riemann (CFR) sense. We rigorously establish the existence and uniqueness of solutions and provide a comprehensive stability analysis. A novel numerical scheme is developed to approximate the system’s dynamics, yielding deeper insights into PP interactions under FO effects. Furthermore, we validate our theoretical findings using numerical simulations, which confirm the robustness and accuracy of the proposed model. The results underline the significance of fractional calculus (FC) in ecological modeling and pave the way for future investigations in population dynamics